CN116137066A - Machine learning-based intelligent identification method and device for house type map functional area - Google Patents
Machine learning-based intelligent identification method and device for house type map functional area Download PDFInfo
- Publication number
- CN116137066A CN116137066A CN202310262705.XA CN202310262705A CN116137066A CN 116137066 A CN116137066 A CN 116137066A CN 202310262705 A CN202310262705 A CN 202310262705A CN 116137066 A CN116137066 A CN 116137066A
- Authority
- CN
- China
- Prior art keywords
- functional area
- pattern
- household
- acquiring
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000010801 machine learning Methods 0.000 title claims abstract description 34
- 238000003062 neural network model Methods 0.000 claims abstract description 97
- 230000006870 function Effects 0.000 claims description 78
- 238000001514 detection method Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 31
- 238000012545 processing Methods 0.000 description 14
- 238000005192 partition Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/36—Indoor scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Abstract
The application provides a machine learning-based intelligent identification method and device for a house type map functional area, wherein the method comprises the following steps: responding to the household pattern functional area identification instruction, and acquiring a household pattern to be identified corresponding to the household pattern functional area identification instruction; acquiring a pre-trained first neural network model, and acquiring a family pattern region in a family pattern to be identified based on the first neural network model; acquiring a pre-trained second neural network model, and acquiring the household pattern functional area identification information in the household pattern area based on the second neural network model; and acquiring the functional area identification information and the functional area identification result included in the household type functional area identification information, and transmitting the functional area identification information and the functional area identification result to the corresponding receiving terminal. According to the method and the device, accurate area distribution of the functional areas of the house type graph and accurate determination of the types of the functional areas are achieved based on the machine learning technology, the functional areas are not required to be divided and identified after the house type graph is manually checked, and the identification efficiency is improved.
Description
Technical Field
The application relates to the technical field of machine learning, in particular to an intelligent identification method and device for a household pattern functional area based on machine learning.
Background
At present, when an indoor designer digitally designs an indoor decoration scheme, the indoor house type sketch needs to be restored or the indoor house type sketch needs to be rebuilt based on the indoor size after the house is measured on site. However, for the house, the general house developer has the house pattern diagram which is designed completely, and the indoor designer is not utilized effectively, so that the indoor designer restores the indoor house pattern sketch or reconstructs the indoor modeling work of the indoor house pattern diagram repeatedly based on the indoor size after the house is measured on site, the cost required for re-drawing is increased, and the completion efficiency of finishing the design diagram is reduced.
Disclosure of Invention
The embodiment of the application provides a machine learning-based house type diagram functional area intelligent identification method and device, and aims to solve the problems that in the prior art, house developers cannot effectively utilize house type diagram indoor designers who finish designs in houses, so that the indoor modeling work of the indoor designers is repeated, the cost required for redrawing is increased, and the finishing efficiency of finishing design diagrams is reduced.
In a first aspect, an embodiment of the present application provides a machine learning-based method for intelligently identifying a functional area of a house type map, including:
Responding to a household pattern functional area identification instruction, and acquiring a household pattern to be identified corresponding to the household pattern functional area identification instruction;
acquiring a pre-trained first neural network model, and acquiring a household pattern area in the household pattern to be identified based on the first neural network model;
acquiring a pre-trained second neural network model, and acquiring household type functional area identification information in the household type image area based on the second neural network model;
and acquiring the functional area identification information and the functional area identification result included in the household type functional area identification information, and transmitting the functional area identification information and the functional area identification result to a corresponding receiving terminal.
In a second aspect, an embodiment of the present application provides a machine learning-based intelligent device for identifying a functional area of a house type map, including:
the system comprises a to-be-identified household pattern acquisition unit, a user identification unit and a user identification unit, wherein the to-be-identified household pattern acquisition unit is used for responding to a household pattern functional area identification instruction and acquiring a to-be-identified household pattern corresponding to the household pattern functional area identification instruction;
the household pattern map area positioning unit is used for acquiring a pre-trained first neural network model and acquiring a household pattern map area in the household pattern map to be identified based on the first neural network model;
the household pattern functional area identification unit is used for acquiring a pre-trained second neural network model and acquiring household pattern functional area identification information in the household pattern area based on the second neural network model;
And the identification result sending unit is used for acquiring the function area identification information and the function area identification result included in the household type function area identification information and sending the function area identification information and the function area identification result to the corresponding receiving terminal.
In a third aspect, an embodiment of the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the machine learning-based house type map functional area intelligent identification method according to the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, where the computer readable storage medium stores a computer program, where the computer program when executed by a processor causes the processor to perform the machine learning-based method for intelligently identifying a functional area of a family pattern according to the first aspect.
The embodiment of the application provides a machine learning-based house type map functional area intelligent identification method and device, wherein the method comprises the following steps: responding to the household pattern functional area identification instruction, and acquiring a household pattern to be identified corresponding to the household pattern functional area identification instruction; acquiring a pre-trained first neural network model, and acquiring a family pattern region in a family pattern to be identified based on the first neural network model; acquiring a pre-trained second neural network model, and acquiring the household pattern functional area identification information in the household pattern area based on the second neural network model; and acquiring the functional area identification information and the functional area identification result included in the household type functional area identification information, and transmitting the functional area identification information and the functional area identification result to the corresponding receiving terminal. According to the method and the device, accurate area distribution of the functional areas of the house type graph and accurate determination of the types of the functional areas are achieved based on the machine learning technology, the functional areas are not required to be divided and identified after the house type graph is manually checked, and the identification efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is an application scenario schematic diagram of a machine learning-based house type map functional area intelligent identification method provided in an embodiment of the present application;
fig. 2 is a flow chart of a machine learning-based intelligent identifying method for a functional area of a house type map according to an embodiment of the present application;
FIG. 3 is a schematic block diagram of a machine learning-based intelligent recognition device for a functional area of a house type map according to an embodiment of the present application;
fig. 4 is a schematic block diagram of a computer device provided in an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic diagram of an application scenario of a machine learning-based house type map functional area intelligent identification method according to an embodiment of the present application; fig. 2 is a flow chart of a machine learning-based intelligent identification method for a functional area of a house type map, which is provided in an embodiment of the present application, and the machine learning-based intelligent identification method for a functional area of a house type map is applied to a server.
As shown in fig. 2, the method includes steps S110 to S140.
S110, responding to the household pattern functional area identification instruction, and acquiring the household pattern to be identified corresponding to the household pattern functional area identification instruction.
In this embodiment, the technical solution is described using a server as an execution body. When the user operation uses a user terminal (such as an intelligent terminal of a smart phone) to upload the household pattern to be identified to the server and clicks the virtual identification button, a corresponding household pattern functional area identification instruction is triggered and generated and sent to the server. The server receives the user pattern diagram functional area identification instruction uploaded by the user terminal, and in order to perform user pattern diagram functional area identification subsequently, the server also needs to acquire a corresponding user pattern diagram to be identified (for example, pdf, jpg, psd and other file format user pattern diagrams to be identified) as an object to be identified.
After the to-be-identified family pattern is obtained, in order to facilitate the subsequent rapid identification of the family pattern functional area, the to-be-identified family pattern may be converted into a unified file format, for example, whether the file format of the to-be-identified family pattern is a jpg format or not, and the initial file format of the to-be-identified family pattern is converted into a preset file format (e.g., the jpg format illustrated above) in the server, so as to update the to-be-identified family pattern.
S120, acquiring a pre-trained first neural network model, and acquiring a household pattern area in the household pattern to be identified based on the first neural network model.
In this embodiment, the first neural network model is used to obtain the family pattern area in the family pattern to be identified in a positioning manner, that is, the first neural network model may use a target detection network to achieve positioning and obtain the family pattern area in the family pattern to be identified. At this time, after the to-be-identified house type graph is identified based on the first neural network model, the to-be-identified house type graph is positioned to a minimum area (such as a minimum polygonal area, a minimum circular area, etc.) which can specifically and completely comprise a house type graph distribution area. Therefore, the region in which the house type map is specifically distributed in the house type map to be identified can be rapidly positioned based on the first neural network model, so that the following focusing on the region is guided to accurately identify the functional region of the house type map.
And after the household pattern areas in the household pattern to be identified are identified by positioning, cutting and removing the areas except the household pattern areas in the household pattern to be identified, so as to obtain the updated household pattern to be identified, wherein only the household pattern areas are reserved.
In an embodiment, as a first embodiment of step S120, step S120 includes:
acquiring a feature map corresponding to the to-be-identified house type map based on an input layer of the first neural network model;
acquiring output features corresponding to the feature map based on the hidden layer of the first neural network model;
and acquiring the house type map area corresponding to the output characteristic based on the output layer of the first neural network model.
In this embodiment, taking the first neural network model as the yoof object detection model as an example, the first neural network model includes an input layer, an encoding layer (i.e. hidden layer, also called hidden layer) corresponding to the yoof object detection algorithm, and an output layer. Based on the network structure, the to-be-identified house type graph can be input to the input layer for processing (such as convolution processing based on a preset convolution kernel) to obtain a feature graph, then output features corresponding to the feature graph in a plurality of coding layers corresponding to a Yolof target detection algorithm are processed (such as full connection processing) based on the output layer of the first neural network model, and finally the house type graph region corresponding to the output features is obtained. And, a classification result with highest confidence can be output correspondingly to the household pattern area (for example, the classification result corresponds to the household pattern). Therefore, the area in which the house type diagram is specifically distributed in the house type diagram to be identified can be rapidly positioned based on the first neural network model.
Wherein the house type graph area comprises a vertex coordinate set of the house type graph; if the house pattern area is determined to be a square area, the vertex coordinate set comprises four vertex coordinates; if the house pattern area is determined to be a non-square area, the vertex coordinate set comprises more than four vertex coordinates. Because the first neural network model is taken as a Yolof target detection model as an example, after the user pattern to be identified is identified based on the first neural network model, a minimum area (such as a minimum polygonal area, a minimum circular area and the like) which can specifically and completely comprise the distribution area of the user pattern is positioned, and at least four vertex coordinates of the minimum area are obtained.
In an embodiment, as a second embodiment of step S120, step S120 includes:
acquiring a feature map corresponding to the to-be-identified house type map based on an input layer of the first neural network model;
acquiring feature similarity of the feature map and each household pattern feature in a local household pattern feature library;
if the feature similarity between the user pattern features and the feature images exceeds a preset similarity threshold, acquiring a corresponding target feature image;
and acquiring a target house type graph area corresponding to the target feature graph as the house type graph area.
In this embodiment, also taking the first neural network model as the yoof object detection model as an example, it includes an input layer, an encoding layer (i.e. hidden layer, also called hidden layer) corresponding to the yoof object detection algorithm, and an output layer. Based on the above network structure, the to-be-identified user pattern may be input to the input layer to be processed (for example, convolution processing is performed based on a preset convolution kernel) to obtain a feature pattern, and then, the difference between the processing of the output features corresponding to the feature pattern in the plurality of coding layers corresponding to the yoof target detection algorithm and the processing of the output features corresponding to the feature pattern in the first embodiment of step S120 is that whether the feature similarity between the user pattern feature and the feature pattern exceeds the preset similarity threshold is searched in the server. If the target feature pattern exists in the server, the method indicates that the server recognizes the same house pattern in the history house pattern recognition process. In order to improve the recognition speed, a target house type map area corresponding to the target feature map in the acquisition server is directly called to serve as the house type map area. Therefore, the area in which the house type diagram is specifically distributed in the house type diagram to be identified can be rapidly positioned based on the first neural network model.
S130, acquiring a pre-trained second neural network model, and acquiring the household pattern functional area identification information in the household pattern area based on the second neural network model.
In this embodiment, when the residential pattern area in the residential pattern to be identified is obtained, which is equivalent to locating only the target large area in which the residential pattern is specifically distributed in the residential pattern to be identified, the accurate identification is not performed on the small area in the residential pattern area, for example, the living room area, the balcony area, the bedroom area, the toilet area, the kitchen area and other residential pattern functional areas in the residential pattern area are not accurately identified yet. At this time, the user pattern area (which is essentially a picture) can be further identified based on a second neural network model pre-trained in the server, so as to obtain more accurate distribution positions of all functional areas and partition types of all functional areas in the user pattern area. Therefore, based on the second neural network model, the distribution position of each functional area in the housekeeping pattern area and the partition type of each functional area can be rapidly identified.
In an embodiment, the second neural network model is a multi-objective detection model, and step S130 includes:
and acquiring a functional area region and a functional area identification type of each functional area in the household pattern region based on the second neural network model aiming at each functional area in the household pattern region so as to form the household pattern functional area identification information.
In this embodiment, if the second neural network model uses a multi-target detection model (such as Yolo V3 multi-target detection model, etc.) as an example, it can be more focused on the distribution position of each functional area in the location type user graph area than the first neural network model, and can identify the partition type (i.e. classification type) of each functional area in the user type user graph area. The identification of each functional area in the household pattern area is to determine the distribution area (i.e. the functional area) of each functional area in the household pattern area, and then obtain the classification type (i.e. the functional area identification type) of each functional area. And after the functional area and the functional area identification type of each functional area are acquired, the household type functional area identification information can be formed.
And S140, acquiring the functional area identification information and the functional area identification result included in the household functional area identification information, and transmitting the functional area identification information and the functional area identification result to a corresponding receiving terminal.
In this embodiment, after the identification information of the household type functional area corresponding to the household type diagram to be identified is obtained, the identification information may be further analyzed and then sent to the receiving terminal for viewing in a form of an identification result including more dimension information. Specifically, after the function area identification information and the function area identification result included in the household type function area identification information are acquired in the server, the function area identification information and the function area identification result are sent to the receiving terminal.
In one embodiment, step S140 includes:
acquiring a functional area region and a functional area identification type of each functional area in the household type functional area identification information to form functional area distribution information;
the method comprises the steps of obtaining a placement identification result of each functional area in the household type functional area identification information and the functional area identification type, and obtaining a functional area identification result of each functional area based on the placement identification result of each functional area in the household type functional area identification information and the functional area identification type.
In this embodiment, after the accurate identification of the family pattern to be identified is performed in the server based on the first neural network model and the second neural network model in sequence to obtain the family pattern functional area identification information, the functional area and the functional area identification type of each functional area can be further obtained.
In order to further confirm whether the function area identification type of each function area is accurate, placement identification (such as a cabinet, a carpet, a chair, a dining table, a television cabinet, a wardrobe, a bed and the like) can be further performed on each function area based on another multi-target detection model trained in advance, so that a placement identification result of each function area is obtained, and the placement identification result of each function area and the function area identification type in the house type function area identification information jointly determine the function area identification result of each function area, so that the accuracy of the identification result is improved.
In an embodiment, the obtaining the function area identification result of each function area based on the placement identification result of each function area in the household type function area identification information and the function area identification type includes:
acquiring an i-th placement identification result and an i-th functional area identification type of an i-th functional area in the house type functional area identification information; wherein, the initial value of i is 1, the value range of i is [1, N ], N is the total number of the functional areas included in the household functional area identification information;
if the association relation between the ith placement object identification result of the ith functional area and the ith functional area identification type is determined, taking the ith functional area identification type as a functional area identification result of the ith functional area;
if it is determined that the i-th placement identification result of the i-th functional area has no association with the i-th functional area identification type, acquiring a pre-trained third neural network model, and acquiring a correction functional area identification type of the i-th functional area based on the third neural network model to serve as a functional area identification result of the i-th functional area;
adding 1 to the i to update the value of i;
if the i is not beyond N, returning to the step of acquiring the i placement identification result and the i functional area identification type of the i functional area in the house type functional area identification information;
And if the i exceeds N, acquiring the function area identification result of the 1 st function area to the function area identification result of the N function area.
In this embodiment, the function area identification result of the 1 st function area in the house type function area identification information is taken as an example. If the 1 st object identification result of the 1 st functional area is determined to be a chair and a dining table, and the 1 st functional area identification type is a restaurant, it can be determined that the 1 st object identification result of the 1 st functional area has an association relationship with the 1 st functional area identification type (namely, the situation that the chair and the dining table are reasonably arranged in the restaurant), and the 1 st functional area identification type can be used as the functional area identification result of the 1 st functional area.
If the 1 st object identification result of the 1 st functional area is determined to be a chair and a dining table, and the 1 st functional area identification type is a bedroom, it may be determined that the 1 st object identification result of the 1 st functional area and the 1 st functional area identification type have no association (i.e. the placement of the chair and the dining table in the bedroom is unreasonable), and at this time, the correction functional area identification type (i.e. the bedroom) of the 1 st functional area may be obtained based on the third neural network model, so as to be used as the functional area identification result of the 1 st functional area. Therefore, the recognition result is further confirmed and corrected based on the mode, so that the recognition result is more accurate.
Therefore, the embodiment of the method realizes the accurate area distribution of the functional areas and the accurate determination of the functional area classification types of the house type graph based on the machine learning technology, does not need to perform functional area classification and identification after the house type graph is manually checked, and improves the identification efficiency.
The embodiment of the application also provides a machine learning-based household pattern functional area intelligent recognition device, which is used for executing any embodiment of the machine learning-based household pattern functional area intelligent recognition method. Specifically, referring to fig. 3, fig. 3 is a schematic block diagram of a machine learning-based home type map functional area intelligent recognition device 100 according to an embodiment of the present application.
As shown in fig. 3, the machine learning-based home pattern functional area intelligent recognition device 100 includes a to-be-recognized home pattern acquisition unit 110, a home pattern area positioning unit 120, a home pattern functional area recognition unit 130, and a recognition result transmission unit 140.
The to-be-identified family pattern obtaining unit 110 is configured to obtain, in response to a family pattern functional area identification instruction, a to-be-identified family pattern corresponding to the family pattern functional area identification instruction.
In this embodiment, the technical solution is described using a server as an execution body. When the user operation uses a user terminal (such as an intelligent terminal of a smart phone) to upload the household pattern to be identified to the server and clicks the virtual identification button, a corresponding household pattern functional area identification instruction is triggered and generated and sent to the server. The server receives the user pattern diagram functional area identification instruction uploaded by the user terminal, and in order to perform user pattern diagram functional area identification subsequently, the server also needs to acquire a corresponding user pattern diagram to be identified (for example, pdf, jpg, psd and other file format user pattern diagrams to be identified) as an object to be identified.
After the to-be-identified family pattern is obtained, in order to facilitate the subsequent rapid identification of the family pattern functional area, the to-be-identified family pattern may be converted into a unified file format, for example, whether the file format of the to-be-identified family pattern is a jpg format or not, and the initial file format of the to-be-identified family pattern is converted into a preset file format (e.g., the jpg format illustrated above) in the server, so as to update the to-be-identified family pattern.
The family pattern region positioning unit 120 is configured to obtain a first neural network model trained in advance, and obtain a family pattern region in the family pattern to be identified based on the first neural network model.
In this embodiment, the first neural network model is used to obtain the family pattern area in the family pattern to be identified in a positioning manner, that is, the first neural network model may use a target detection network to achieve positioning and obtain the family pattern area in the family pattern to be identified. At this time, after the to-be-identified house type graph is identified based on the first neural network model, the to-be-identified house type graph is positioned to a minimum area (such as a minimum polygonal area, a minimum circular area, etc.) which can specifically and completely comprise a house type graph distribution area. Therefore, the region in which the house type map is specifically distributed in the house type map to be identified can be rapidly positioned based on the first neural network model, so that the following focusing on the region is guided to accurately identify the functional region of the house type map.
And after the household pattern areas in the household pattern to be identified are identified by positioning, cutting and removing the areas except the household pattern areas in the household pattern to be identified, so as to obtain the updated household pattern to be identified, wherein only the household pattern areas are reserved.
In an embodiment, as a first embodiment of the family pattern area positioning unit 120, the family pattern area positioning unit 120 is specifically configured to:
acquiring a feature map corresponding to the to-be-identified house type map based on an input layer of the first neural network model;
acquiring output features corresponding to the feature map based on the hidden layer of the first neural network model;
and acquiring the house type map area corresponding to the output characteristic based on the output layer of the first neural network model.
In this embodiment, taking the first neural network model as the yoof object detection model as an example, the first neural network model includes an input layer, an encoding layer (i.e. hidden layer, also called hidden layer) corresponding to the yoof object detection algorithm, and an output layer. Based on the network structure, the to-be-identified house type graph can be input to the input layer for processing (such as convolution processing based on a preset convolution kernel) to obtain a feature graph, then output features corresponding to the feature graph in a plurality of coding layers corresponding to a Yolof target detection algorithm are processed (such as full connection processing) based on the output layer of the first neural network model, and finally the house type graph region corresponding to the output features is obtained. And, a classification result with highest confidence can be output correspondingly to the household pattern area (for example, the classification result corresponds to the household pattern). Therefore, the area in which the house type diagram is specifically distributed in the house type diagram to be identified can be rapidly positioned based on the first neural network model.
Wherein the house type graph area comprises a vertex coordinate set of the house type graph; if the house pattern area is determined to be a square area, the vertex coordinate set comprises four vertex coordinates; if the house pattern area is determined to be a non-square area, the vertex coordinate set comprises more than four vertex coordinates. Because the first neural network model is taken as a Yolof target detection model as an example, after the user pattern to be identified is identified based on the first neural network model, a minimum area (such as a minimum polygonal area, a minimum circular area and the like) which can specifically and completely comprise the distribution area of the user pattern is positioned, and at least four vertex coordinates of the minimum area are obtained.
In one embodiment, as the second embodiment of the step-type-map-area positioning unit 120, the step-type-map-area positioning unit 120 is specifically configured to:
acquiring a feature map corresponding to the to-be-identified house type map based on an input layer of the first neural network model;
acquiring feature similarity of the feature map and each household pattern feature in a local household pattern feature library;
if the feature similarity between the user pattern features and the feature images exceeds a preset similarity threshold, acquiring a corresponding target feature image;
And acquiring a target house type graph area corresponding to the target feature graph as the house type graph area.
In this embodiment, also taking the first neural network model as the yoof object detection model as an example, it includes an input layer, an encoding layer (i.e. hidden layer, also called hidden layer) corresponding to the yoof object detection algorithm, and an output layer. Based on the above network structure, the to-be-identified user pattern may be input to the input layer to be processed (for example, convolution processing is performed based on a preset convolution kernel) to obtain a feature pattern, and then, the difference between the processing of the output features corresponding to the feature pattern in the plurality of coding layers corresponding to the yoof target detection algorithm and the processing of the output features corresponding to the feature pattern in the first embodiment of step S120 is that whether the feature similarity between the user pattern feature and the feature pattern exceeds the preset similarity threshold is searched in the server. If the target feature pattern exists in the server, the method indicates that the server recognizes the same house pattern in the history house pattern recognition process. In order to improve the recognition speed, a target house type map area corresponding to the target feature map in the acquisition server is directly called to serve as the house type map area. Therefore, the area in which the house type diagram is specifically distributed in the house type diagram to be identified can be rapidly positioned based on the first neural network model.
The household pattern functional area identifying unit 130 is configured to obtain a pre-trained second neural network model, and obtain household pattern functional area identifying information in the household pattern area based on the second neural network model.
In this embodiment, when the residential pattern area in the residential pattern to be identified is obtained, which is equivalent to locating only the target large area in which the residential pattern is specifically distributed in the residential pattern to be identified, the accurate identification is not performed on the small area in the residential pattern area, for example, the living room area, the balcony area, the bedroom area, the toilet area, the kitchen area and other residential pattern functional areas in the residential pattern area are not accurately identified yet. At this time, the user pattern area (which is essentially a picture) can be further identified based on a second neural network model pre-trained in the server, so as to obtain more accurate distribution positions of all functional areas and partition types of all functional areas in the user pattern area. Therefore, based on the second neural network model, the distribution position of each functional area in the housekeeping pattern area and the partition type of each functional area can be rapidly identified.
In an embodiment, the second neural network model is a multi-objective detection model, and the household-type functional area identifying unit 130 is specifically configured to:
And acquiring a functional area region and a functional area identification type of each functional area in the household pattern region based on the second neural network model aiming at each functional area in the household pattern region so as to form the household pattern functional area identification information.
In this embodiment, if the second neural network model uses a multi-target detection model (such as Yolo V3 multi-target detection model, etc.) as an example, it can be more focused on the distribution position of each functional area in the location type user graph area than the first neural network model, and can identify the partition type (i.e. classification type) of each functional area in the user type user graph area. The identification of each functional area in the household pattern area is to determine the distribution area (i.e. the functional area) of each functional area in the household pattern area, and then obtain the classification type (i.e. the functional area identification type) of each functional area. And after the functional area and the functional area identification type of each functional area are acquired, the household type functional area identification information can be formed.
And an identification result transmitting unit 140, configured to acquire the functional area identification information and the functional area identification result included in the household type functional area identification information, and transmit the functional area identification information and the functional area identification result to a corresponding receiving terminal.
In this embodiment, after the identification information of the household type functional area corresponding to the household type diagram to be identified is obtained, the identification information may be further analyzed and then sent to the receiving terminal for viewing in a form of an identification result including more dimension information. Specifically, after the function area identification information and the function area identification result included in the household type function area identification information are acquired in the server, the function area identification information and the function area identification result are sent to the receiving terminal.
In one embodiment, the identification result sending unit 140 is specifically configured to:
acquiring a functional area region and a functional area identification type of each functional area in the household type functional area identification information to form functional area distribution information;
the method comprises the steps of obtaining a placement identification result of each functional area in the household type functional area identification information and the functional area identification type, and obtaining a functional area identification result of each functional area based on the placement identification result of each functional area in the household type functional area identification information and the functional area identification type.
In this embodiment, after the accurate identification of the family pattern to be identified is performed in the server based on the first neural network model and the second neural network model in sequence to obtain the family pattern functional area identification information, the functional area and the functional area identification type of each functional area can be further obtained.
In order to further confirm whether the function area identification type of each function area is accurate, placement identification (such as a cabinet, a carpet, a chair, a dining table, a television cabinet, a wardrobe, a bed and the like) can be further performed on each function area based on another multi-target detection model trained in advance, so that a placement identification result of each function area is obtained, and the placement identification result of each function area and the function area identification type in the house type function area identification information jointly determine the function area identification result of each function area, so that the accuracy of the identification result is improved.
In an embodiment, the obtaining the function area identification result of each function area based on the placement identification result of each function area in the household type function area identification information and the function area identification type includes:
acquiring an i-th placement identification result and an i-th functional area identification type of an i-th functional area in the house type functional area identification information; wherein, the initial value of i is 1, the value range of i is [1, N ], N is the total number of the functional areas included in the household functional area identification information;
if the association relation between the ith placement object identification result of the ith functional area and the ith functional area identification type is determined, taking the ith functional area identification type as a functional area identification result of the ith functional area;
If it is determined that the i-th placement identification result of the i-th functional area has no association with the i-th functional area identification type, acquiring a pre-trained third neural network model, and acquiring a correction functional area identification type of the i-th functional area based on the third neural network model to serve as a functional area identification result of the i-th functional area;
adding 1 to the i to update the value of i;
if the i is not beyond N, returning to the step of acquiring the i placement identification result and the i functional area identification type of the i functional area in the house type functional area identification information;
and if the i exceeds N, acquiring the function area identification result of the 1 st function area to the function area identification result of the N function area.
In this embodiment, the function area identification result of the 1 st function area in the house type function area identification information is taken as an example. If the 1 st object identification result of the 1 st functional area is determined to be a chair and a dining table, and the 1 st functional area identification type is a restaurant, it can be determined that the 1 st object identification result of the 1 st functional area has an association relationship with the 1 st functional area identification type (namely, the situation that the chair and the dining table are reasonably arranged in the restaurant), and the 1 st functional area identification type can be used as the functional area identification result of the 1 st functional area.
If the 1 st object identification result of the 1 st functional area is determined to be a chair and a dining table, and the 1 st functional area identification type is a bedroom, it may be determined that the 1 st object identification result of the 1 st functional area and the 1 st functional area identification type have no association (i.e. the placement of the chair and the dining table in the bedroom is unreasonable), and at this time, the correction functional area identification type (i.e. the bedroom) of the 1 st functional area may be obtained based on the third neural network model, so as to be used as the functional area identification result of the 1 st functional area. Therefore, the recognition result is further confirmed and corrected based on the mode, so that the recognition result is more accurate.
Therefore, the embodiment of the device realizes the accurate area distribution of the functional areas and the accurate determination of the functional area classification types of the house type map based on the machine learning technology, does not need to manually check the house type map and then perform functional area classification and identification, and improves the identification efficiency.
The above-described machine learning-based house pattern functional area intelligent recognition apparatus may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 4.
Referring to fig. 4, fig. 4 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 is a server or a cluster of servers.
Referring to fig. 4, the computer apparatus 500 includes a processor 502, a memory, and a network interface 505, which are connected by a device bus 501, wherein the memory may include a storage medium 503 and an internal memory 504.
The storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032, when executed, causes the processor 502 to perform a machine learning based method for intelligently identifying functional areas of a family pattern.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the execution of a computer program 5032 in the storage medium 503, which computer program 5032, when executed by the processor 502, causes the processor 502 to perform a machine learning based method for intelligently identifying functional areas of a family pattern.
The network interface 505 is used for network communication, such as providing for transmission of data information, etc. Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of a portion of the architecture in connection with the present application and is not intended to limit the computer device 500 to which the present application is applied, and that a particular computer device 500 may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
The processor 502 is configured to execute a computer program 5032 stored in a memory, so as to implement the machine learning-based house type map functional area intelligent identification method disclosed in the embodiments of the present application.
Those skilled in the art will appreciate that the embodiment of the computer device shown in fig. 4 is not limiting of the specific construction of the computer device, and in other embodiments, the computer device may include more or less components than those shown, or certain components may be combined, or a different arrangement of components. For example, in some embodiments, the computer device may include only a memory and a processor, and in such embodiments, the structure and function of the memory and the processor are consistent with the embodiment shown in fig. 4, and will not be described again.
It should be appreciated that in embodiments of the present application, the processor 502 may be a Central processing unit (Central ProcessingUnit, CPU), and the processor 502 may also be other general purpose processors, digital signal processors (DigitalSignalProcessor, DSP), application specific integrated circuits (ApplicationSpecificIntegrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-ProgrammableGateArray, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In another embodiment of the present application, a computer-readable storage medium is provided. The computer readable storage medium may be a nonvolatile computer readable storage medium or a volatile computer readable storage medium. The computer readable storage medium stores a computer program, wherein the computer program realizes the intelligent identification method of the household pattern functional area based on machine learning disclosed in the embodiment of the application when being executed by a processor.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus, device and unit described above may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein. Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus, device, and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, for example, the division of the units is merely a logical function division, there may be another division manner in actual implementation, or units having the same function may be integrated into one unit, for example, multiple units or components may be combined or may be integrated into another apparatus, or some features may be omitted, or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purposes of the embodiments of the present application.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units may be stored in a storage medium if implemented in the form of software functional units and sold or used as stand-alone products. Based on such understanding, the technical solution of the present application is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a background server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. The intelligent identifying method for the house type map functional area based on machine learning is characterized by comprising the following steps:
responding to a household pattern functional area identification instruction, and acquiring a household pattern to be identified corresponding to the household pattern functional area identification instruction;
acquiring a pre-trained first neural network model, and acquiring a household pattern area in the household pattern to be identified based on the first neural network model;
acquiring a pre-trained second neural network model, and acquiring household type functional area identification information in the household type image area based on the second neural network model;
and acquiring the functional area identification information and the functional area identification result included in the household type functional area identification information, and transmitting the functional area identification information and the functional area identification result to a corresponding receiving terminal.
2. The method of claim 1, wherein the obtaining, based on the first neural network model, a family pattern region in the family pattern to be identified comprises:
Acquiring a feature map corresponding to the to-be-identified house type map based on an input layer of the first neural network model;
acquiring output features corresponding to the feature map based on the hidden layer of the first neural network model;
and acquiring the house type map area corresponding to the output characteristic based on the output layer of the first neural network model.
3. The method of claim 1, wherein the obtaining, based on the first neural network model, a family pattern region in the family pattern to be identified comprises:
acquiring a feature map corresponding to the to-be-identified house type map based on an input layer of the first neural network model;
acquiring feature similarity of the feature map and each household pattern feature in a local household pattern feature library;
if the feature similarity between the user pattern features and the feature images exceeds a preset similarity threshold, acquiring a corresponding target feature image;
and acquiring a target house type graph area corresponding to the target feature graph as the house type graph area.
4. The method of claim 1, wherein the house pattern area comprises a vertex coordinate set of the house pattern; if the house pattern area is determined to be a square area, the vertex coordinate set comprises four vertex coordinates; if the house pattern area is determined to be a non-square area, the vertex coordinate set comprises more than four vertex coordinates.
5. The method of claim 1, wherein the second neural network model is a multi-objective detection model; the obtaining the identifying information of the household type functional area in the household type graph area based on the second neural network model comprises the following steps:
and acquiring a functional area region and a functional area identification type of each functional area in the household pattern region based on the second neural network model aiming at each functional area in the household pattern region so as to form the household pattern functional area identification information.
6. The method according to claim 5, wherein the acquiring the function area identification information and the function area identification result included in the house type function area identification information includes:
acquiring a functional area region and a functional area identification type of each functional area in the household type functional area identification information to form functional area distribution information;
the method comprises the steps of obtaining a placement identification result of each functional area in the household type functional area identification information and the functional area identification type, and obtaining a functional area identification result of each functional area based on the placement identification result of each functional area in the household type functional area identification information and the functional area identification type.
7. The method of claim 6, wherein the obtaining the function area identification result of each function area based on the placement identification result of each function area in the household type function area identification information and the function area identification type comprises:
acquiring an i-th placement identification result and an i-th functional area identification type of an i-th functional area in the house type functional area identification information; wherein, the initial value of i is 1, the value range of i is [1, N ], N is the total number of the functional areas included in the household functional area identification information;
if the association relation between the ith placement object identification result of the ith functional area and the ith functional area identification type is determined, taking the ith functional area identification type as a functional area identification result of the ith functional area;
if it is determined that the i-th placement identification result of the i-th functional area has no association with the i-th functional area identification type, acquiring a pre-trained third neural network model, and acquiring a correction functional area identification type of the i-th functional area based on the third neural network model to serve as a functional area identification result of the i-th functional area;
adding 1 to the i to update the value of i;
if the i is not beyond N, returning to the step of acquiring the i placement identification result and the i functional area identification type of the i functional area in the house type functional area identification information;
And if the i exceeds N, acquiring the function area identification result of the 1 st function area to the function area identification result of the N function area.
8. Machine learning-based house type map functional area intelligent recognition device is characterized by comprising:
the system comprises a to-be-identified household pattern acquisition unit, a user identification unit and a user identification unit, wherein the to-be-identified household pattern acquisition unit is used for responding to a household pattern functional area identification instruction and acquiring a to-be-identified household pattern corresponding to the household pattern functional area identification instruction;
the household pattern map area positioning unit is used for acquiring a pre-trained first neural network model and acquiring a household pattern map area in the household pattern map to be identified based on the first neural network model;
the household pattern functional area identification unit is used for acquiring a pre-trained second neural network model and acquiring household pattern functional area identification information in the household pattern area based on the second neural network model;
and the identification result sending unit is used for acquiring the function area identification information and the function area identification result included in the household type function area identification information and sending the function area identification information and the function area identification result to the corresponding receiving terminal.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the machine learning based house pattern functional area intelligent recognition method according to any one of claims 1-7 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program, which when executed by a processor causes the processor to perform the machine learning based house pattern functional area intelligent identification method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310262705.XA CN116137066A (en) | 2023-03-17 | 2023-03-17 | Machine learning-based intelligent identification method and device for house type map functional area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310262705.XA CN116137066A (en) | 2023-03-17 | 2023-03-17 | Machine learning-based intelligent identification method and device for house type map functional area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116137066A true CN116137066A (en) | 2023-05-19 |
Family
ID=86326867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310262705.XA Pending CN116137066A (en) | 2023-03-17 | 2023-03-17 | Machine learning-based intelligent identification method and device for house type map functional area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116137066A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408935A (en) * | 2018-10-17 | 2019-03-01 | 东易日盛家居装饰集团股份有限公司 | A kind of region partitioning method and device |
| CN110059721A (en) * | 2019-03-16 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Floor plan area recognizing method, device, equipment and computer readable storage medium |
| CN110096949A (en) * | 2019-03-16 | 2019-08-06 | 平安城市建设科技(深圳)有限公司 | Floor plan intelligent identification Method, device, equipment and computer readable storage medium |
| CN110728235A (en) * | 2019-10-11 | 2020-01-24 | 广东三维家信息科技有限公司 | House type area marking method and device |
| KR102142347B1 (en) * | 2019-10-01 | 2020-08-07 | 주식회사 카카오뱅크 | Method for id card recognition and application for the same method |
| CN115424287A (en) * | 2022-08-05 | 2022-12-02 | 万翼科技有限公司 | Functional area identification and model construction method, equipment and storage medium thereof |
-
2023
- 2023-03-17 CN CN202310262705.XA patent/CN116137066A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408935A (en) * | 2018-10-17 | 2019-03-01 | 东易日盛家居装饰集团股份有限公司 | A kind of region partitioning method and device |
| CN110059721A (en) * | 2019-03-16 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Floor plan area recognizing method, device, equipment and computer readable storage medium |
| CN110096949A (en) * | 2019-03-16 | 2019-08-06 | 平安城市建设科技(深圳)有限公司 | Floor plan intelligent identification Method, device, equipment and computer readable storage medium |
| KR102142347B1 (en) * | 2019-10-01 | 2020-08-07 | 주식회사 카카오뱅크 | Method for id card recognition and application for the same method |
| CN110728235A (en) * | 2019-10-11 | 2020-01-24 | 广东三维家信息科技有限公司 | House type area marking method and device |
| CN115424287A (en) * | 2022-08-05 | 2022-12-02 | 万翼科技有限公司 | Functional area identification and model construction method, equipment and storage medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220053287A1 (en) | Localization determination for mixed reality systems | |
| EP3343399A1 (en) | Device and method for processing metadata | |
| WO2022267285A1 (en) | Robot pose determination method and apparatus, robot and storage medium | |
| WO2007072391A2 (en) | Automatic 3-d object detection | |
| CN109857893A (en) | Picture retrieval method, device, computer equipment and storage medium | |
| CN113362314B (en) | Medical image recognition method, recognition model training method and device | |
| CN116310918A (en) | Indoor key object identification and positioning method, device and equipment based on mixed reality | |
| CN109858402B (en) | Image detection method, device, terminal and storage medium | |
| CN108597589B (en) | Model generation method, target detection method and medical imaging system | |
| US11657611B2 (en) | Methods and systems for augmented reality room identification based on room-object profile data | |
| CN113889214A (en) | Data processing system for acquiring target text | |
| CN105740777A (en) | Information processing method and device | |
| US11654572B2 (en) | Robot mapping method and robot and computer readable storage medium using the same | |
| CN116137066A (en) | Machine learning-based intelligent identification method and device for house type map functional area | |
| WO2021128731A1 (en) | Image processing method and apparatus, image processing device, and storage medium | |
| CN114638921A (en) | Motion capture method, terminal device, and storage medium | |
| CN114285984B (en) | Camera switching method and device based on AR (augmented reality) glasses, storage medium and terminal | |
| KR102322995B1 (en) | Method for artificial intelligence nodule segmentation based on dynamic window and apparatus thereof | |
| CN114496246A (en) | Method and device for evaluating posture health and storage medium | |
| CN113191462A (en) | Information acquisition method, image processing method and device and electronic equipment | |
| CN115549822A (en) | Method, device, equipment and storage medium for human body perception in space | |
| CN113780176B (en) | Local occlusion object identification method, device, equipment and storage medium | |
| WO2022181253A1 (en) | Joint point detection device, teaching model generation device, joint point detection method, teaching model generation method, and computer-readable recording medium | |
| WO2019056331A1 (en) | Method and device for controlling cooking apparatus, computer storage medium, and system | |
| CN117688654A (en) | Indoor design system based on image processing technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |